Autonomous Driving Control Using Scenario-Specific Algorithms
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional motion planning and control systems for autonomous vehicles do not accurately account for differences in vehicle types, leading to inconsistent and potentially unsafe navigation, as they rely solely on speed and curvature without considering specific driving scenarios.
Innovation Solution
A scenario-based control system that determines the current driving scenario using multiple sensed inputs, allowing for the selection and application of distinct control algorithms tailored to specific conditions, such as aggressive steering in parking scenarios or smooth steering in normal driving, to generate appropriate control commands for throttle, steering, and braking.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the same motion planning and control algorithm is applied to all vehicle types, then the system complexity is reduced and ease of operation is improved, but the manufacturing precision and reliability of navigation are worsened due to inability to account for vehicle-specific characteristics
Solution Approach 1:
The patent implements scenario-based control that applies different control algorithms tailored to specific driving scenarios (e.g., aggressive steering for parking, smooth steering for normal driving). This allows the system to optimize performance for each scenario while maintaining a unified architecture, resolving the contradiction between system simplicity and scenario-specific precision.
Solution Approach 2:
The system dynamically selects and switches between different control algorithms based on the current driving scenario detected by the scenario decision module. This dynamic adaptation enables the system to maintain high precision across varying conditions without requiring a completely different system for each scenario.
2Device complexity
If conventional motion planning estimates difficulty based only on curvature and speed, then the measurement process is simplified, but the measurement precision is worsened due to lack of scenario-specific considerations
Solution Approach 1:
The patent adds a new dimension to motion planning by introducing scenario classification as an additional parameter beyond traditional curvature and speed. The scenario decision module evaluates multiple inputs (vehicle speed, steering angle, brake pedal position, gear position) to determine the current driving scenario, enabling more precise difficulty estimation without significantly increasing system complexity.
3Reliability
If different control algorithms are used for different driving scenarios, then the reliability and adaptability are improved, but the device complexity increases due to multiple algorithms and scenario detection requirements
Solution Approach 1:
The control system is segmented into distinct modules: scenario decision module that detects driving scenarios, and multiple distinct control algorithms (e.g., parking control module, normal driving control module) that are selectively activated. This modular architecture improves reliability through scenario-specific optimization while managing complexity through clear separation of functions.
Solution Approach 2:
The unified control system serves multiple functions by integrating scenario detection and multiple control algorithms into a single platform. The system can adaptively switch between parking control, normal driving control, and other scenario-specific controls, achieving multi-functionality without requiring completely separate systems for each scenario.
Data Source
AI summary
In one embodiment, control of an autonomous driving vehicle (ADV) includes determining a current scenario of the ADV. Based on the scenario, a control algorithm is selected among a plurality of distinct control algorithms as the active control algorithm. One or more control commands are generated using the active control algorithm, based one or more target inputs. The control commands are applied to effect movement of the ADV.